This paper presents an interesting and novel idea of a deep learning (DL) framework to segment potentially cancerous areas in prostate biopsies using semi-automatically generated data. The application of this paper is quite innovative and the proposed method seems to be a direct assistance to the clinical routine.
The Centre for Medical Imaging Science and Visualization (CMIV) at Linköping University is developing a new database for medical images and pathology images to offer training data for new artificial intelligence-based (AI) products